Skip to content
Navigation menu
Search
Powered by Algolia
Search
Log in
Create account
DEV Community
Close
#
latency
Follow
Hide
Posts
Left menu
đź‘‹
Sign in
for the ability to sort posts by
relevant
,
latest
, or
top
.
Right menu
Best-of-N is prepaid retries: the cost math of racing parallel attempts
Walker Miller
Walker Miller
Walker Miller
Follow
Aug 9
Best-of-N is prepaid retries: the cost math of racing parallel attempts
#
retries
#
cost
#
latency
#
failuremodes
Comments
Add Comment
5 min read
Your token bill is the cheap part: dimensioning the real cost of an agent
Walker Miller
Walker Miller
Walker Miller
Follow
Aug 9
Your token bill is the cheap part: dimensioning the real cost of an agent
#
cost
#
latency
#
tokens
#
operations
Comments
Add Comment
7 min read
Twelve LLMs Played Werewolf. The Real Wolf Was the Thinking Knob.
Tommy Leonhardsen
Tommy Leonhardsen
Tommy Leonhardsen
Follow
Aug 11
Twelve LLMs Played Werewolf. The Real Wolf Was the Thinking Knob.
#
llm
#
benchmarks
#
reasoning
#
latency
1
 reaction
Comments
Add Comment
8 min read
How I tried to write an article about slow Chinese LLMs
Aliaksei Zelianouski
Aliaksei Zelianouski
Aliaksei Zelianouski
Follow
Aug 6
How I tried to write an article about slow Chinese LLMs
#
ai
#
llm
#
benchmarks
#
latency
17
 reactions
Comments
16
 comments
10 min read
How Fast Should Your AI Voice Agent Respond?
Pykero
Pykero
Pykero
Follow
Jul 14
How Fast Should Your AI Voice Agent Respond?
#
voiceai
#
latency
#
aiagents
#
customerservice
2
 reactions
Comments
2
 comments
4 min read
The 50ms promise I made in v1.6
Ravi Patel
Ravi Patel
Ravi Patel
Follow
Jun 6
The 50ms promise I made in v1.6
#
ai
#
api
#
edge
#
latency
Comments
Add Comment
5 min read
Putting Prism's front door on every continent
Ravi Patel
Ravi Patel
Ravi Patel
Follow
Jun 5
Putting Prism's front door on every continent
#
ai
#
api
#
edge
#
latency
Comments
Add Comment
6 min read
A voice agent is not a chatbot with a phone number
Arthur
Arthur
Arthur
Follow
Jun 18
A voice agent is not a chatbot with a phone number
#
voiceai
#
aiagents
#
llm
#
latency
2
 reactions
Comments
1
 comment
9 min read
How we slashed an AI Agent's latency by 80% in 60 minutes
Frank Guan
Frank Guan
Frank Guan
Follow
for
Google AI
Jul 1
How we slashed an AI Agent's latency by 80% in 60 minutes
#
agents
#
latency
#
gemini
#
webdev
12
 reactions
Comments
1
 comment
1 min read
The caller heard silence for two seconds before the agent spoke
Marcus Chen
Marcus Chen
Marcus Chen
Follow
Jul 7
The caller heard silence for two seconds before the agent spoke
#
voiceagents
#
latency
#
python
#
ai
Comments
Add Comment
6 min read
5 LLM APIs Tested for Latency: Real Data [2026]
Kunal
Kunal
Kunal
Follow
Jun 14
5 LLM APIs Tested for Latency: Real Data [2026]
#
llmapi
#
aibenchmarks
#
latency
#
gpt41
Comments
1
 comment
13 min read
Building Low-Latency Trading Bots: Architecting Real-Time WebSocket Streams
mountek
mountek
mountek
Follow
Jun 9
Building Low-Latency Trading Bots: Architecting Real-Time WebSocket Streams
#
algorithmictrading
#
websockets
#
systemdesign
#
latency
Comments
Add Comment
4 min read
đź‘‹
Sign in
for the ability to sort posts by
relevant
,
latest
, or
top
.
We're a place where coders share, stay up-to-date and grow their careers.
Log in
Create account